Here in Week 4 of 12 of the MATS Program, we’re required to submit a brief “project abstract” describing what we’re up to, as well as a much longer “theory of change” imagining how our work could have a positive impact on AI safety. Given the tight word count requirements, I completely cheated by uploading a pdf with a long block quote at the start and a deeply technical footnote, neither of which I counted, and I still turned it in late. I maintain that I did all this to exp

0. This is compaction (technical background) LLMs don’t experience time the way we do. We perceive the present not as an instant but as an extended present, a brief duration measuring about three seconds. But LLMs live in a massively extended present. When you talk to an LLM, it replays the entire session from the start each time before adding the next token (roughly, the next word). It does this over and over every time it reads and writes, meaning its extended present keeps